Transform Your Ideas
Into Stunning Images
DreamPixel Forge is a modern GUI for running multiple AI image generation models locally on your machine.
LLM Enhanced Prompting: Use local language models to convert descriptions into optimal tags or enhance existing prompts for better results.
Multiple models supported
Image Gallery
Check out some examples of images generated with DreamPixel Forge - from stunning landscapes and cityscapes to professional app icons with automatic platform-specific sizing.
Prompt:
Cyberpunk female warrior in a futuristic setting
Prompt:
Surreal landscape with floating islands and mystical purple atmosphere
Prompt:
Clean, professional app icon with automatic platform-specific sizing for iOS, Android, macOS, and Windows
Prompt:
Minimalist forest scene with geometric shapes and natural lighting
Prompt:
Modern cityscape with sleek architecture and contemporary urban design
Prompt:
Sleek futuristic spaceship design with detailed sci-fi elements
Powerful Features
DreamPixel Forge comes packed with features to help you create stunning AI-generated images with ease.
LLM Enhanced Prompting
Improve your results with local LLMs that enhance your tags or convert descriptions into optimized prompt tags, all running on your machine.
Description to Tags
Enter a detailed description of what you want to see, and the local LLM converts it into 5-10 optimized image generation tags.
Enhance Existing Tags
Refine your existing prompts with 3-5 additional closely related keywords that improve results while maintaining style and concept.
Multi-Model Support
Run various AI models locally including Stable Diffusion 1.5, 2.1, XL, Dreamlike Diffusion, Kandinsky 2.2, and Pony Diffusion V6 XL. Import custom models from CIVITAI and other sources.
Text-to-Image Generation
Transform your text prompts into stunning images with various models and customizable parameters.
Batch Image Generation
Generate up to 10 images at once with the same prompt to explore different variations.
Model-Specific Presets
Optimized resolution presets and tag recommendations for each model to get the best quality output. Each model has tailored settings for optimal results.
App Icon Generation
Create professional app icons with specialized presets. Includes post-processing tools for rounded corners and automatic platform-specific sizing for iOS, Android, macOS, and Windows applications.
Cross-Platform Support
Works on Windows, macOS, and Linux with GPU acceleration where available.
LLM Enhanced Prompting
DreamPixel Forge uses locally running language models to enhance your prompts for superior image generation results.
Harness the Power of Local LLMs
Description to Tags Conversion
Enter descriptive sentences of what you want to see, and our LLM integration will convert them into 5-10 optimized image generation tags.
Input: "A futuristic city at night with neon signs and flying cars"
Output: "futuristic cityscape, night scene, neon lights, flying vehicles, cyberpunk, urban landscape, high-rise buildings, sci-fi, detailed, atmospheric"
Enhance Existing Tags
Already have a set of tags? Let our LLM enhance them with 3-5 additional closely related keywords to improve your results while maintaining the original style and concept.
Input: "mountain landscape, sunset, pine trees"
Output: "mountain landscape, sunset, pine trees, golden hour, majestic peaks, alpine scenery, dramatic sky"
Privacy-Focused
Since all processing is done locally on your machine, your prompts and creative ideas remain private and secure. No data is sent to external servers.
Ollama Integration
Seamlessly works with Ollama to provide language model capabilities without requiring a connection to cloud services. Choose from various language models based on your needs and system capabilities.
Model Customization
Select different language models based on your specific needs and hardware capabilities, from lightweight models for basic enhancement to more advanced models for complex prompt refinement.
Supported Models
DreamPixel Forge supports a variety of AI image generation models, each with its own strengths and characteristics. All models support a range of resolutions to fit your needs.
Custom Model Support
Import your own custom models from CIVITAI and other sources. DreamPixel Forge automatically detects and configures model types (SD 1.5, SD 2.1, SDXL) with appropriate settings for optimal performance.
Stable Diffusion 1.5
The classic model that started it all. Great for general purpose image generation with a good balance of speed and quality.
Size
~4GB
VRAM
4GB+
Stable Diffusion 2.1
Improved version with better image quality and more consistent results. Good for detailed images and realistic scenes.
Size
~4.2GB
VRAM
4GB+
Stable Diffusion XL
Latest generation with significantly improved image quality, composition, and prompt following. Best for high-quality outputs.
Size
~6.5GB
VRAM
8GB+
Dreamlike Diffusion
Specialized model that produces dreamy, artistic images with vibrant colors and unique style.
Size
~4GB
VRAM
4GB+
Kandinsky 2.2
Russian alternative to Stable Diffusion with its own unique aesthetic and strengths in certain types of imagery.
Size
~4.5GB
VRAM
4GB+
Pony Diffusion V6 XL
Specialized model based on SDXL architecture, optimized for stylized art generation.
Size
~7GB
VRAM
8GB+
Download DreamPixel Forge
Get started with DreamPixel Forge today and transform your text prompts into stunning AI-generated images.
System Requirements
Minimum
- • Python 3.8 or higher
- • 8GB RAM
- • 4GB free disk space per model
- • CPU only (slow generation)
Recommended
- • Python 3.8 or higher
- • 16GB RAM
- • NVIDIA GPU with 8GB+ VRAM
- • 20GB free disk space for all models
Quick Installation
# Clone the repository
git clone https://github.com/Legorobotdude/dream-pixel-forge.git
cd dream-pixel-forge
# Create a virtual environment (recommended)
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install the required packages
pip3 install -r requirements.txt
# Run the application
python3 dream_pixel_forge.pyFor detailed installation instructions and troubleshooting, please refer to the GitHub repository.